© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 15667
    Prev
    Next
    INDEX
    Explanations

    specific programming-related keywords and code snippets

    oai_token-act-pair · gpt-3.5-turbo

    references to hourly wage and checkout-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naire
    -0.94
    ative
    -0.90
    atively
    -0.79
    iture
    -0.77
    atives
    -0.74
    naires
    -0.73
    ife
    -0.72
    Õ
    -0.69
    atform
    -0.69
    itures
    -0.69
    POSITIVE LOGITS
    {{
    0.79
    henko
    0.78
    bats
    0.73
    CHAT
    0.73
    phrine
    0.72
    ynchronous
    0.72
    ocr
    0.70
    xon
    0.69
    reci
    0.67
    }}
    0.67
    Activations Density 0.025%

    No Known Activations